Contrastive Attention-Based Network for Self-Supervised Point Cloud Completion
Point cloud completion aims to reconstruct complete 3D shapes from partial observations, often requiring multiple views or complete data for training. In this paper, we propose an attention-driven, self-supervised autoencoder network that completes 3D point clouds from a single partial observation....
Uloženo v:
| Vydáno v: | IEEE signal processing letters Ročník 32; s. 4444 - 4448 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
New York
IEEE
2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Témata: | |
| ISSN: | 1070-9908, 1558-2361 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Point cloud completion aims to reconstruct complete 3D shapes from partial observations, often requiring multiple views or complete data for training. In this paper, we propose an attention-driven, self-supervised autoencoder network that completes 3D point clouds from a single partial observation. Multi-head self-attention captures robust contextual relationships, while residual connections in the autoencoder enhance geometric feature learning. In addition to this, we incorporate a contrastive learning-based loss, which encourages the network to better distinguish structural patterns even in highly incomplete observations. Experimental results on benchmark datasets demonstrate that the proposed approach achieves state-of-the-art performance in single-view point cloud completion. |
|---|---|
| AbstractList | Point cloud completion aims to reconstruct complete 3D shapes from partial observations, often requiring multiple views or complete data for training. In this paper, we propose an attention-driven, self-supervised autoencoder network that completes 3D point clouds from a single partial observation. Multi-head self-attention captures robust contextual relationships, while residual connections in the autoencoder enhance geometric feature learning. In addition to this, we incorporate a contrastive learning-based loss, which encourages the network to better distinguish structural patterns even in highly incomplete observations. Experimental results on benchmark datasets demonstrate that the proposed approach achieves state-of-the-art performance in single-view point cloud completion. |
| Author | Kumar, Preyum Kumari, Seema Raman, Shanmuganathan Mandal, Srimanta |
| Author_xml | – sequence: 1 givenname: Seema orcidid: 0000-0003-3305-6871 surname: Kumari fullname: Kumari, Seema email: seema.kumari@iitgn.ac.in organization: Department of Electrical Engineering, IIT Gandhinagar, Gandhinagar, India – sequence: 2 givenname: Preyum orcidid: 0000-0001-5622-1468 surname: Kumar fullname: Kumar, Preyum email: preyum.kumar@iitgn.ac.in organization: Department of Electrical Engineering, IIT Gandhinagar, Gandhinagar, India – sequence: 3 givenname: Srimanta orcidid: 0000-0003-3871-6621 surname: Mandal fullname: Mandal, Srimanta email: srimanta_mandal@dau.ac.in organization: Dhirubhai Ambani University (formerly DA-IICT), Gandhinagar, India – sequence: 4 givenname: Shanmuganathan orcidid: 0000-0003-2718-7891 surname: Raman fullname: Raman, Shanmuganathan email: shanmuga@iitgn.ac.in organization: Department of Electrical Engineering, IIT Gandhinagar, Gandhinagar, India |
| BookMark | eNpFkF1LwzAUhoNMcJvee-FFwevMfDe5nMUvGHMwvQ5ZmkJn19QknfjvbdnAq3PgPO974JmBSetbB8AtRguMkXpYbTcLgghfUEExI-wCTDHnEhIq8GTYUY6gUkhegVmMe4SQxJJPwbrwbQompvrosmVKrk21b-Gjia7M1i79-PCVVT5kW9dUcNt3Lhzr8bbxdZuyovF9mRX-0DVuDF6Dy8o00d2c5xx8Pj99FK9w9f7yVixX0GJBElSk2pUSWW6UEoTREhGKDLOK70gpFGaK212ucs6kFYJSbC3OMTeScmpKV9E5uD_1dsF_9y4mvfd9aIeXmpJcIDa04oFCJ8oGH2Nwle5CfTDhV2OkR2t6sKZHa_psbYjcnSK1c-4fx4QqJgn9AxxfaYs |
| CODEN | ISPLEM |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025 |
| DBID | 97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| DOI | 10.1109/LSP.2025.3631424 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Technology Research Database |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1558-2361 |
| EndPage | 4448 |
| ExternalDocumentID | 10_1109_LSP_2025_3631424 11239482 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: Jibaben Patel Chair in Artificial Intelligence, IIT Gandhinagar, India |
| GroupedDBID | -~X .DC 0R~ 29I 3EH 4.4 5GY 5VS 6IK 85S 97E AAJGR AASAJ AAWTH AAYJJ ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TAE TN5 VH1 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c162t-92fbd80c5a996243d0230a4c95b2d691495cb797548c66331cc1715a8353adef3 |
| IEDL.DBID | RIE |
| ISSN | 1070-9908 |
| IngestDate | Thu Nov 27 15:42:55 EST 2025 Sat Nov 29 06:50:42 EST 2025 Wed Dec 10 09:47:03 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c162t-92fbd80c5a996243d0230a4c95b2d691495cb797548c66331cc1715a8353adef3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0003-3871-6621 0000-0003-2718-7891 0000-0003-3305-6871 0000-0001-5622-1468 |
| PQID | 3276046241 |
| PQPubID | 75747 |
| PageCount | 5 |
| ParticipantIDs | ieee_primary_11239482 proquest_journals_3276046241 crossref_primary_10_1109_LSP_2025_3631424 |
| PublicationCentury | 2000 |
| PublicationDate | 20250000 2025-00-00 20250101 |
| PublicationDateYYYYMMDD | 2025-01-01 |
| PublicationDate_xml | – year: 2025 text: 20250000 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE signal processing letters |
| PublicationTitleAbbrev | LSP |
| PublicationYear | 2025 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| SSID | ssj0008185 |
| Score | 2.4386249 |
| Snippet | Point cloud completion aims to reconstruct complete 3D shapes from partial observations, often requiring multiple views or complete data for training. In this... |
| SourceID | proquest crossref ieee |
| SourceType | Aggregation Database Index Database Publisher |
| StartPage | 4444 |
| SubjectTerms | and self-supervision Auto-encoder Autoencoders contrastive learning Decoding Image reconstruction multi-head self-attention Noise point cloud completion Point cloud compression Semantics Shape Surface reconstruction Three dimensional models Three-dimensional displays Training Transformers |
| Title | Contrastive Attention-Based Network for Self-Supervised Point Cloud Completion |
| URI | https://ieeexplore.ieee.org/document/11239482 https://www.proquest.com/docview/3276046241 |
| Volume | 32 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-2361 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0008185 issn: 1070-9908 databaseCode: RIE dateStart: 19940101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA46POjBnxOnU3Lw4iFbm7RNcpzD4UHGYAq7lTRJYTDasbX-_ealnT8QD94K_UF5ab_3fcl7XxC6z3JwOZcxSayMSOSSCBFKOpWijE6yMBaSar_ZBJ9OxWIhZ22zuu-Fsdb64jM7gEO_lm9KXcNU2dBxAyYj4RB3n_Okadb6hF3IPE2BYUAcxIrdmmQghy_zmVOCNB6whEFn148c5DdV-YXEPr1MTv75YqfouOWReNQM_Bnas8U5OvrmLniBpuA8tVFbADQ8qqqmsJE8urxl8LQp_8aOs-K5XeVkXq8BNuDcrFwWFR6vytpgwAvw5y6LLnqbPL2On0m7fQLRYUIrImmeGRHoWDlNQyNmQG6oSMs4oyaRII10xiV3mkU73sFCrUMexspxMqaMzdkl6hRlYa8QZgpsxHIV8kw7ZDVCBcI6ZqG45pTFpocedgFN141LRurVRSBTF_wUgp-2we-hLgTw67o2dj3U3w1B2v5H25RRnkD7bBRe_3HbDTqEpzezIn3UqTa1vUUH-r1abjd3_hP5AGcmt-s |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1dS8MwFA0yBfXBz4nTqX3wxYdsbdKP5HEOx8RZBpuwt5ImKQxGO7bO329u2vmB-OBboS0tN-255yT3niB0n2bgcs4DHGruY98kEcwENypFKBmmXsA4kXaziSiO2WzGx3Wzuu2F0Vrb4jPdgUO7lq8KuYGpsq7hBpT7zCDubuD7xK3atT6BF3JPVWLoYgOybLsq6fLuaDI2WpAEHRpS6O36kYXstiq_sNgmmMHxP1_tBB3VTNLpVUN_inZ0foYOv_kLnqMYvKdWYg2Q5vTKsiptxI8mcyknrgrAHcNanYleZHiyWQJwwLlxMc9Lp78oNsoBxACH7iJvorfB07Q_xPUGClh6ISkxJ1mqmCsDYVQN8akCwSF8yYOUqJCDOJJpxCOjWqRhHtST0ou8QBhWRoXSGb1AjbzI9SVyqAAjsUx4USoNtiomXKYNtxCRjAgNVAs9bAOaLCufjMTqC5cnJvgJBD-pg99CTQjg13V17FqovR2CpP6T1gklUQgNtL539cdtd2h_OH0dJaPn-OUaHcCTqjmSNmqUq42-QXvyvZyvV7f2c_kAJyG7Mg |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Contrastive+Attention-Based+Network+for+Self-Supervised+Point+Cloud+Completion&rft.jtitle=IEEE+signal+processing+letters&rft.au=Kumari%2C+Seema&rft.au=Kumar%2C+Preyum&rft.au=Mandal%2C+Srimanta&rft.au=Raman%2C+Shanmuganathan&rft.date=2025&rft.issn=1070-9908&rft.eissn=1558-2361&rft.spage=1&rft.epage=5&rft_id=info:doi/10.1109%2FLSP.2025.3631424&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_LSP_2025_3631424 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1070-9908&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1070-9908&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1070-9908&client=summon |